A spatial-spectral transformer combined with active transfer learning and uncertainty-driven sample selection is reported to improve cross-domain hyperspectral image classification with fewer labels.
A fast and compact hybrid cnn for hyperspectral imaging-based bloodstain classification,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Transformer-Driven Active Transfer Learning for Cross-Hyperspectral Image Classification
A spatial-spectral transformer combined with active transfer learning and uncertainty-driven sample selection is reported to improve cross-domain hyperspectral image classification with fewer labels.